Abstract #301133

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301133
Activity Number: 84
Type: Contributed
Date/Time: Monday, August 4, 2003 : 8:30 AM to 10:20 AM
Sponsor: Business & Economics Statistics Section
Abstract - #301133
Title: A Comparative Study of Three New Methods of Instrument Selection in Econometrics
Author(s): Kalidas Jana*+ and Alastair Hall
Companies: North Carolina State University and North Carolina State University
Address: Department of Economics, Raleigh, NC, 27695-0001,
Keywords: instrument selection ; canonical correlations information criterion ; relevant moments selection criterion ; approximate mean square error ; two-stage least squares ; higher-order asymptotics
Abstract:

Implementation of the instrumental variables (IV) method of estimation requires choice of a set of instruments by the practitioner. Such choice has been informal at best. Recently, a number of instrument selection criteria has been proposed in the literature. This paper relates to three among these proposed criteria, namely, the Canonical Correlations Information Criterion (CCIC), the Relevant Moments Selection Criterion (RMSC) and the Approximate Mean Square Error Criterion (MSE). Although properties of each of these methods have been explored by their proponents, there have been to date no comparative studies of these methods. This paper intends to fill that gap. To this end, it (i) establishes a relation between contemporaneous and long run canonical correlations in a linear simultaneous equation model; (ii) compares the CCIC, the RMSC and the MSE both analytically and empirically in the context of a simple linear IV model; and (iii) assesses the relative performance of these three methods via a simulation study by investigating the finite sample behavior of the postselection estimator of this simple IV model.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003